Structs§
- Chat
Message - Chat
Metadata - Execution evidence recorded by the runtime/provider (not by the model).
- Chat
Request - Chat
Response - Chat
Stream Summary - Terminal stream summary. It deliberately omits the full text, so a stream never forces the runtime to buffer unbounded output.
- Generation
Capabilities - Optional features of a generation provider. The OpenAI-compatible adapter cannot discover these, so they are configured and enforced up front.
- Generation
Model Info - Generation
Options - Provider
Capabilities - Provider
Capability - Tool
Call - A tool-call proposal produced by a model. It is not evidence that the operation ran, was authorized, or would succeed; the calling application decides whether and how to execute it.
- Tool
Definition - A tool the model may propose to call. The runtime never executes it: the schema constrains the proposed arguments and grants no authority.
- Usage
- Token accounting as reported by the provider; never estimated.
Enums§
- Chat
Role - Chat
Stream Event - Execution
Location - Finish
Reason - Why generation stopped, when the provider says.
Otherpreserves an unrecognized provider value verbatim. - Response
Format - Requested output shape.
JsonSchemais a request to the provider; it is never a guarantee. The runtime validates the result separately. - Structured
Output - Result of checking generated text against the requested format.
- Tool
Choice - Provider-neutral tool selection policy. Absent means the provider default.
Constants§
- DEFAULT_
MAX_ OUTPUT_ BYTES - Default upper bound on accumulated generated output (4 MiB).
- MAX_
TOOL_ NAME_ BYTES - Longest tool name accepted (matches common provider limits).
Traits§
- Generation
Provider - A provider of generative inference. Separate from
crate::Provider, which serves typed inference. - Provider
Functions§
- is_
valid_ tool_ name - Tool names are restricted to
[A-Za-z0-9_-]{1,64}so they are safe on every provider wire and in logs.